Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
throw4847285
on Dec 20, 2024
|
parent
|
context
|
favorite
| on:
Alignment faking in large language models
That's not true. There's a whole section on challenges to that definition. See: 5. The Connectionist Challenge.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: